Risk assessment of thyroid nodules with a multi-instance convolutional neural network
These results demonstrate the effectiveness and clinical utility of the proposed MIL-CNN framework in non-invasively stratifying thyroid nodule risk, supporting more informed clinical decisions and potentially reducing unnecessary biopsies and surgeries. Codes will be available at GitHub - rrrr-ops/Thyroid-AI.
Authors
- Hebin Zhang (ORCID: https://orcid.org/0000-0001-5459-9408)
- Jiacheng Wang (ORCID: https://orcid.org/0009-0004-3270-0252)
- Yu Da
- Tingting Song (ORCID: https://orcid.org/0000-0002-2305-2300)
- Feng Gao (ORCID: https://orcid.org/0000-0002-3031-0021)
- Zirong Wang (ORCID: https://orcid.org/0009-0006-1385-2693)
- Yancheng Yu (ORCID: https://orcid.org/0009-0004-0979-1803)
Institutions
- Harbin Medical University (CN)
- Xiamen University (CN)
- Affiliated Hospital of Hangzhou Normal University (CN)
- Fourth Affiliated Hospital of Harbin Medical University (CN)
- Xiamen University of Technology (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-07-24
- DOI
- https://doi.org/10.3389/fonc.2025.1608963
- Citations
- 2
- Primary Topic
- Thyroid Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 2.59